--- title: Leveraging LLMs in your Obsidian Notes · Ollama Blog description: A walkthrough for building an Obsidian plugin that lets you chat with your notes using local LLMs via Ollama. Covers indexing markdown notes with Llama Index... canonical: https://daily.dev/posts/leveraging-llms-in-your-obsidian-notes-ollama-blog-nxlgpkrob twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Leveraging LLMs in your Obsidian Notes · Ollama Blog | daily.dev og:description: A walkthrough for building an Obsidian plugin that lets you chat with your notes using local LLMs via Ollama. Covers indexing markdown notes with Llama Index... og:url: https://daily.dev/posts/leveraging-llms-in-your-obsidian-notes-ollama-blog-nxlgpkrob og:image: https://api.daily.dev/og/posts/nXLgpKrOb.png og:image:alt: Leveraging LLMs in your Obsidian Notes · Ollama Blog og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Leveraging LLMs in your Obsidian Notes · Ollama Blog **[Ollama](https://daily.dev/sources/ollama)** · 6 min read · 0 upvotes · 0 comments ## Summary A walkthrough for building an Obsidian plugin that lets you chat with your notes using local LLMs via Ollama. Covers indexing markdown notes with Llama Index (embeddings, chunking at 256 tokens), retrieving the top relevant chunks for a query, feeding them into a system prompt, and generating answers with the llama2 model through the ollama-node library. Also suggests extensions like summarization, keyword extraction, and generating flashcards for Anki. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do I let users ask questions about their Obsidian notes using a local LLM? Index notes with an embeddings library like Llama Index, splitting text into chunks (e.g. 256 tokens), then at query time retrieve the top-K most similar chunks (e.g. top 5) and insert them into a system prompt sent to a local model such as llama2 via Ollama. The model then answers using only that retrieved context, avoiding the need to feed entire vaults into the model at once. _daily.dev surfaces practical RAG patterns for developers wiring local LLMs into note-taking apps._ ### Why can't I just feed my entire notes vault into an LLM prompt at once? Most models have limited input context size, so you cannot hand over an entire notes vault in one prompt. Instead, notes need to be split into chunks, embedded, and searched by concept similarity rather than exact keyword match, then only the most relevant chunks (for example the top 5 matches) are passed to the model as context. _Developers hitting context-window limits can track LLM context and RAG techniques on daily.dev._ ## Similar posts on daily.dev - [I fed my entire Obsidian vault into a local LLM, and now it actually understands my research](https://daily.dev/posts/i-fed-my-entire-obsidian-vault-into-a-local-llm-and-now-it-actually-understands-my-research-x5g1g21pk) · XDA Developers · 2 upvotes · 0 comments - [Integrating LLMs with Ollama and Spring AI](https://daily.dev/posts/integrating-llms-with-ollama-and-spring-ai-ftjw4akn6) · codecentric · 0 upvotes · 0 comments - [Ollama for JavaScript Developers](https://daily.dev/posts/ollama-for-javascript-developers-m7eti7jpi) · SitePoint · 0 upvotes · 0 comments - [How to Run an LLM Locally to Interact with Your Documents](https://daily.dev/posts/how-to-run-an-llm-locally-to-interact-with-your-documents-zxekby3xw) · freeCodeCamp · 4 upvotes · 0 comments - [How to Integrate Local LLMs With Ollama and Python Quiz – Real Python](https://daily.dev/posts/how-to-integrate-local-llms-with-ollama-and-python-quiz-real-python-o2fgipyca) · Real Python · 3 upvotes · 0 comments --- Tags: [#rag](https://daily.dev/tags/rag), [#embeddings](https://daily.dev/tags/embeddings), [#ollama](https://daily.dev/tags/ollama), [#llama](https://daily.dev/tags/llama) [View this post on daily.dev](https://daily.dev/posts/leveraging-llms-in-your-obsidian-notes-ollama-blog-nxlgpkrob) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Leveraging LLMs in your Obsidian Notes · Ollama Blog","url":"https://daily.dev/posts/leveraging-llms-in-your-obsidian-notes-ollama-blog-nxlgpkrob","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/leveraging-llms-in-your-obsidian-notes-ollama-blog-nxlgpkrob"},"datePublished":"2026-08-23T12:23:53.297Z","dateModified":"2026-08-23T12:57:38.416Z","description":"A walkthrough for building an Obsidian plugin that lets you chat with your notes using local LLMs via Ollama. Covers indexing markdown notes with Llama Index...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/03fb1a10ef158f8986c9778334c2af42?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/03fb1a10ef158f8986c9778334c2af42?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Ollama","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Ollama","logo":"https://media.daily.dev/image/upload/s--dRYYkBCj--/f_auto,q_auto/v1787487632/logos/ollama-blog?_a=BAMAMicg0","url":"https://daily.dev/sources/ollama"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/leveraging-llms-in-your-obsidian-notes-ollama-blog-nxlgpkrob","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"rag,embeddings,ollama,llama","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Ollama","item":"https://daily.dev/sources/ollama"},{"@type":"ListItem","position":3,"name":"Leveraging LLMs in your Obsidian Notes · Ollama Blog"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/leveraging-llms-in-your-obsidian-notes-ollama-blog-nxlgpkrob#faq","mainEntity":[{"@type":"Question","name":"How do I let users ask questions about their Obsidian notes using a local LLM?","acceptedAnswer":{"@type":"Answer","text":"Index notes with an embeddings library like Llama Index, splitting text into chunks (e.g. 256 tokens), then at query time retrieve the top-K most similar chunks (e.g. top 5) and insert them into a system prompt sent to a local model such as llama2 via Ollama. The model then answers using only that retrieved context, avoiding the need to feed entire vaults into the model at once. daily.dev surfaces practical RAG patterns for developers wiring local LLMs into note-taking apps."}},{"@type":"Question","name":"Why can't I just feed my entire notes vault into an LLM prompt at once?","acceptedAnswer":{"@type":"Answer","text":"Most models have limited input context size, so you cannot hand over an entire notes vault in one prompt. Instead, notes need to be split into chunks, embedded, and searched by concept similarity rather than exact keyword match, then only the most relevant chunks (for example the top 5 matches) are passed to the model as context. Developers hitting context-window limits can track LLM context and RAG techniques on daily.dev."}}]} ```